智慧交通信標(Intelligent Traffic Beacon, ITB)是以無線訊號嗅探技術為基礎的交通資料收集裝置，在范雲瀚 (2017)及梁騰駿 (2019)的研究中陸續提出了一車多機、車道判斷及運具分類此三大問題與解法，然而其研究資料皆來自封閉式場域的模擬實驗，本研究為首次將ITB的實驗場域轉移到實際道路——汐止高速公路段，嘗試用一字型的ITB擺設收集大量真實資料，並以人工智慧影像辨識資料作為真值來源。
一字型的ITB佈設方式，使車輛上的智慧型裝置與ITB的接觸時間縮短，再加上高速公路的高車流量、高車速、多車道，讓訊號收集變得更加困難。此外，在實際場域無法以白名單實驗的方式取得真值，因此如何辨別無線訊號來自影像資料中的哪一輛車，成為了本研究須解決的課題。
另外由於高速公路的車種、車道、以及車內手機的數量和品牌，排列組合是一個龐大數目，但其數目是有限的，因此本研究提出以深度學習方法解決車道判斷問題，期待未來模型的訓練完成之後，ITB能夠做為獨立的交通資料收集工具。

Intelligent Traffic Beacon (ITB) is a traffic data collection device based on wireless sniffing technology. In the research of Fan (2017) and Liang (2019), Multiple Devices Problem, Lane Identification Problem and Transportation Mode Problem were successively proposed. However, the research data are all derived from simulation experiments in a closed field. Our research is the first time to transfer the experimental field of ITB to actual field—the highway, trying to collect a large amount of real data with two ITB installed on the ETC(Electronic Toll Collection) gate, and use the data from artificial intelligence-based traffic flow recognition system as truth value.

The in-line ITB topology shortens the contact window between the smart device on the vehicle and the ITB, coupled with the high traffic volume, high speed, and multiple lanes on the highway, signal collection becomes more difficult. In addition, it is impossible to obtain the truth value by means of whitelist experiments in the actual field. Therefore, how to identify which car the wireless signal comes from has become a subject to be solved in this research.

In addition, the permutation and combination of the number of vehicles, lanes, and the number and brands of smart devices in the car is a huge but limited number. Therefore, this research proposes to solve Lane Identification Problem with deep learning method so the ITB can be used as an independent traffic data collection device in the future.

周建銘、李威勳、陳朝烈（2020）。「整合車流智慧辨識與無線嗅探技術之高速公路交通管理策略」計畫書。
范雲瀚（2017）。以智慧車輛探測達成時空無縫隙之交通資料蒐集框架。國立成功大學交通管理科學系碩士論文。
梁騰駿（2019）。以機器學習進行無線嗅探技術之交通資料分析。國立成功大學交通管理科學系碩士論文。
Ang, C. (2018, 5-8 Feb. 2018). Vehicle positioning using WIFI fingerprinting in urban environment. Paper presented at the 2018 IEEE 4th World Forum on Internet of Things (WF-IoT).
Boudabous, S., Garbiso, J., Leroy, B., Clemencon, S., & Labiod, H. (2019, 28 April-1 May 2019). Traffic Analysis Based on Bluetooth Passive Scanning. Paper presented at the 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring).
Chen, C., Ota, K., Dong, M., Yu, C., & Jin, H. (2020). WITM: Intelligent Traffic Monitoring Using Fine-Grained Wireless Signal. IEEE Transactions on Emerging Topics in Computational Intelligence, 4(3), 206-215.
Chen, Z., Zou, H., Yang, J., Jiang, H., & Xie, L. (2020). WiFi Fingerprinting Indoor Localization Using Local Feature-Based Deep LSTM. IEEE Systems Journal, 14(2), 3001-3010.
Cvetek, D., Horenec, I., Muštra, M., & Jelušić, N. (2019, 23-25 Sept. 2019). Analysis of Correlation Between Dwell Time Measured Using Bluetooth Detector and Occupancy. Paper presented at the 2019 International Symposium ELMAR.
Goodall, N. (2016). Fundamental Characteristics of Wi-Fi and Wireless Local Area Network Re-identification for Transportation. IET Intelligent Transport Systems, 11.
Haferkamp, M., Al-Askary, M., Dorn, D., Sliwa, B., Habel, L., Schreckenberg, M., & Wietfeld, C. (2017, 4-7 June 2017). Radio-Based Traffic Flow Detection and Vehicle Classification for Future Smart Cities. Paper presented at the 2017 IEEE 85th Vehicular Technology Conference (VTC Spring).
He, K., Zhang, X., Ren, S., & Sun, J. (2016, 27-30 June 2016). Deep Residual Learning for Image Recognition. Paper presented at the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-term Memory. Neural computation, 9, 1735-1780.
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., & Muller, P.-A. (2019). Deep learning for time series classification: a review. Data Mining and Knowledge Discovery, 33(4), 917-963.
Ismail Fawaz, H., Lucas, B., Forestier, G., Pelletier, C., Schmidt, D., Weber, J., . . . Petitjean, F. (2020). InceptionTime: Finding AlexNet for time series classification. Data Mining and Knowledge Discovery, 34, 1-27.
Laharotte, P. A., Billot, R., Come, E., Oukhellou, L., Nantes, A., & El Faouzi, N. E. (2015). Spatiotemporal Analysis of Bluetooth Data: Application to a Large Urban Network. IEEE Transactions on Intelligent Transportation Systems, 16(3), 1439-1448.
Lange, S., & Riedmiller, M. (2010, 18-23 July 2010). Deep auto-encoder neural networks in reinforcement learning. Paper presented at the The 2010 International Joint Conference on Neural Networks (IJCNN).
Lines, J., Taylor, S., & Bagnall, A. (2016, 12-15 Dec. 2016). HIVE-COTE: The Hierarchical Vote Collective of Transformation-Based Ensembles for Time Series Classification. Paper presented at the 2016 IEEE 16th International Conference on Data Mining (ICDM).
Seok, K. Y., & Lee, J. H. (2020, 19-21 Feb. 2020). Deep Learning Based Fingerprinting Scheme for Wireless Positioning. Paper presented at the 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC).
Tinh, P. D., & Mai, T. T. N. (2020, 28-29 Aug. 2020). Mobile Indoor Positioning System Utilizing WiFi RSSI and Motion Data. Paper presented at the 2020 4th International Conference on Recent Advances in Signal Processing, Telecommunications & Computing (SigTelCom).
Won, M., Sahu, S., & Park, K.-J. (2019). DeepWiTraffic: Low Cost WiFi-Based Traffic Monitoring System Using Deep Learning.
Xu, B., Zhu, X., & Zhu, H. (2019). An Efficient Indoor Localization Method Based on the Long Short-Term Memory Recurrent Neuron Network. IEEE Access, 7, 123912-123921.